Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15827
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.08
    0.2%
    219
    +0.07
    0.2%
    394
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1446
    +0.08
    0.03
    2033
    +0.07
    0.04
    884
    +0.07
    0.02
    Negative Logits
     withal
    -0.56
     impelled
    -0.54
     quitted
    -0.54
     resurre
    -0.53
     Pyrénées
    -0.53
     omits
    -0.50
     idr
    -0.50
     Madura
    -0.49
     endeav
    -0.49
     Incidentally
    -0.49
    POSITIVE LOGITS
     preghi
    0.66
     swarovski
    0.58
    🔑
    0.57
     récomp
    0.56
     nutella
    0.56
     iscri
    0.56
     dirait
    0.56
     farsi
    0.55
     virtù
    0.55
     servire
    0.55
    Activations Density 0.292%

    No Known Activations